[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip / qa] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/g/ - Technology

Name
Options
Comment
Verification
4chan Pass users can bypass this verification. [Learn More] [Login]
File
  • Please read the Rules and FAQ before posting.
  • You may highlight syntax and preserve whitespace by using [code] tags.

08/21/20New boards added: /vrpg/, /vmg/, /vst/ and /vm/
05/04/17New trial board added: /bant/ - International/Random
10/04/16New board for 4chan Pass users: /vip/ - Very Important Posts
[Hide] [Show All]


[Advertise on 4chan]


File: PW_76934_.jpg (500 KB, 2560x1536)
500 KB
500 KB JPG
Previous /sdg/ thread : >>101530296

>Beginner UI local install
EasyDiffusion: https://easydiffusion.github.io
Fooocus: https://github.com/lllyasviel/fooocus
Metastable: https://metastable.studio

>Local install
Automatic1111: https://github.com/automatic1111/stable-diffusion-webui
ComfyUI: https://github.com/comfyanonymous/ComfyUI
SD.Next: https://github.com/vladmandic/automatic
AMD GPU: https://rentry.org/sdg-link#amd-gpu
Intel GPU: https://rentry.org/sdg-link#intel-gpu

>Use a VAE if your images look washed out
https://rentry.org/sdvae

>Run cloud hosted instance
https://rentry.org/sdg-link#run-cloud-hosted-instance

>SD3 info & download
https://rentry.org/sdg-link#sd3

>Try online without registration
sd3: https://huggingface.co/spaces/stabilityai/stable-diffusion-3-medium
txt2img: https://www.mage.space
img2img: https://huggingface.co/spaces/huggingface/diffuse-the-rest

>Models, LoRAs & upscaling
https://civitai.com
https://huggingface.co
https://aitracker.art
https://openmodeldb.info

>Animation
https://rentry.org/AnimAnon
https://rentry.org/AnimAnon-AnimDiff
https://rentry.org/AnimAnon-Deforum

>Index of guides and other tools
https://rentry.org/sdg-link
https://rentry.org/rentrysd

>View and submit GPU performance data
https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html
https://docs.getgrist.com/3mjouqRSdkBY/sdperformance

>Share image prompt info
4chan removes prompt info from images, share them with the following guide/site...
https://rentry.org/hdgcb
https://catbox.moe

>Discord
6wUwtcJsr2

>Related boards
>>>/h/hdg
>>>/e/edg
>>>/d/ddg
>>>/b/degen
>>>/vt/vtai
>>>/aco/sdg
>>>/trash/sdg
>>
what's the best anime model these days?* I want to try something new.

*excluding NovelAI obviously
>>
File: _DG_News_00018_.png (1.83 MB, 1560x896)
1.83 MB
1.83 MB PNG
>mfw Resource news

07/23/2024

>Mammoth - An Extendible (General) Continual Learning Framework for Pytorch
https://github.com/aimagelab/mammoth

>Differentiable Convex Polyhedra Optimization from Multi-view Images
https://github.com/kimren227/DiffConvex

>Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models
https://maxin-cn.github.io/cinemo_project

>Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models
https://github.com/georgiarg/AutoFashion

07/22/2024

>Intel AI Playground beta Official Launch
https://game.intel.com/us/stories/introducing-ai-playground/

>SD3 Unbanned: Community Decision on Its Future at Civitai
https://civitai.com/articles/6221/sd3-unbanned-community-decision-on-its-future-at-civitai

>GenTron: Diffusion Transformers for Image and Video Generation
https://github.com/lavinal712/GenTron

>ComfyUI-Lumina-Next-SFT-DiffusersWrapper
https://github.com/Excidos/ComfyUI-Lumina-Next-SFT-DiffusersWrapper

>PhotoMaker V2 Released with improved ID fidelity
https://github.com/TencentARC/PhotoMaker#-new-featuresupdates

>T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation
https://t2v-compbench.github.io/

>ComfyUI_FL-Trainer: Train Loras in ComfyUI
https://github.com/filliptm/ComfyUI_FL-Trainer/tree/main

>Video Diffusion Alignment via Reward Gradient
https://github.com/mihirp1998/VADER

>Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation
https://github.com/LiuJF1226/Mono-ViFI

>RealViformer: Investigating Attention for Real-World Video Super-Resolution
https://github.com/Yuehan717/RealViformer

>PlacidDreamer: Advancing Harmony in Text-to-3D Generation
https://github.com/HansenHuang0823/PlacidDreamer

07/21/2024

>Batched Runge-Kutta Samplers for ComfyUI
https://github.com/wootwootwootwoot/ComfyUI-RK-Sampler
>>
>mfw Research news

07/23/2024

>Artist: Aesthetically Controllable Text-Driven Stylization without Training
https://diffusionartist.github.io/

>SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
https://arxiv.org/abs/2407.15841

>Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
https://arxiv.org/abs/2407.15811

>The Impact of Responsible AI Research on Innovation and Development
https://arxiv.org/abs/2407.15647

>Synthetic Image Learning: Preserving Performance and Preventing Membership Inference Attacks
https://arxiv.org/abs/2407.15526

>SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time
https://arxiv.org/abs/2407.15507

>DiffX: Guide Your Layout to Cross-Modal Generative Modeling
https://arxiv.org/abs/2407.15488

>Diverse Image Harmonization
https://arxiv.org/abs/2407.15481

>Text2Place : Affordance Aware Human Guided Placement
https://rishubhpar.github.io/Text2Place/

>Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data
https://arxiv.org/abs/2407.15383

>Attention Beats Linear for Fast Implicit Neural Representation Generation
https://arxiv.org/abs/2407.15355

>Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models
https://arxiv.org/abs/2407.15328

>BIGbench: A Unified Benchmark for Social Bias in Text-to-Image Generative Models Based on Multi-modal LLM
https://arxiv.org/abs/2407.15240

>CGB-DM: Content and Graphic Balance Layout Generation with Transformer-based Diffusion Model
https://arxiv.org/abs/2407.15233

>HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions
https://zhouhyocean.github.io/holodreamer

>Assessing Sample Quality via the Latent Space of Generative Models
https://arxiv.org/abs/2407.15171

>Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification
https://arxiv.org/abs/2407.15155
>>
>>101544262
pony mixes. try autismmix (not joking)
>>
File: 000000_15259_.png (2.37 MB, 998x1459)
2.37 MB
2.37 MB PNG
>>101544069
TY Baker!
>>
>mfw MORE Research news

>Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification
https://arxiv.org/abs/2407.15155

>D4M: Dataset Distillation via Disentangled Diffusion Model
https://arxiv.org/abs/2407.15138

>D4-VTON: Dynamic Semantics Disentangling for Differential Diffusion based Virtual Try-On
https://arxiv.org/abs/2407.15111

>LSReGen: Large-Scale Regional Generator via Backward Guidance Framework
https://arxiv.org/abs/2407.15066

>GreenStableYolo: Optimizing Inference Time and Image Quality of T2I Generation
https://arxiv.org/abs/2407.14982

>Falcon2-11B Technical Report
https://arxiv.org/abs/2407.14885

>Text-based Talking Video Editing with Cascaded Conditional Diffusion
https://arxiv.org/abs/2407.14841

>Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding
https://arxiv.org/abs/2407.14816

>FairViT: Fair Vision Transformer via Adaptive Masking
https://arxiv.org/abs/2407.14799

>Intelligent Artistic Typography: Comprehensive Review of Artistic Text Design and Generation
https://arxiv.org/abs/2407.14774

>Audio-visual training for improved grounding in video-text LLMs
https://arxiv.org/abs/2407.15046

>Rethinking Domain Adaptation and Generalization in the Era of CLIP
https://arxiv.org/abs/2407.15173

>MIBench: Evaluating Multimodal LLMs over Multiple Images
https://arxiv.org/abs/2407.15272

>Assessing Brittleness of Image-Text Retrieval Benchmarks from VLMs Perspective
https://arxiv.org/abs/2407.15239

>SIGMA:Sinkhorn-Guided Masked Video Modeling
https://arxiv.org/abs/2407.15447

>Predicting the Best of N Visual Trackers
https://arxiv.org/abs/2407.15707

>Robust Facial Reactions Generation: Emotion-Aware Framework with Modality Compensation
https://arxiv.org/abs/2407.15798

>Reconstructing Training Data From Models Trained with Transfer Learning
https://arxiv.org/abs/2407.15845

>In-Context Learning Improves Compositional Understanding of VLMs
https://arxiv.org/abs/2407.15487
>>
File: PW_76901_.jpg (427 KB, 2560x1536)
427 KB
427 KB JPG
>>101544504
Any time!! :D
>>
File: tmp6lxopjuk.png (1.19 MB, 768x1024)
1.19 MB
1.19 MB PNG
I may or may not created a glimpse in how AI "hybridization" works.

I'd post the catbox, but 4chan keeps claiming it's spam
>>
File: 00122-2260212785.jpg (755 KB, 1024x1536)
755 KB
755 KB JPG
>>
Actually, maybe it'll work now?

https://litter.catbox.moe/6widk6.png
>>
File: PW_76886_.jpg (206 KB, 2560x1536)
206 KB
206 KB JPG
>>
File: tmpmte1mkat.png (1.26 MB, 896x1152)
1.26 MB
1.26 MB PNG
>>
File: de_re_ap_00034_.png (2.77 MB, 2016x1152)
2.77 MB
2.77 MB PNG
>>101544674
that settles it, I'm making a chibi prompt
oh, also, fran officially crossed the 100k threshold today
>>
File: file.jpg (512 KB, 1792x1024)
512 KB
512 KB JPG
another big data banger dropped!
>https://huggingface.co/datasets/bigdata-pw/playground
>Job manager crashed while running this job (missing heartbeats).
>Error code: JobManagerCrashedError
crashed the dataset viewer, 2big4u. annoying because i wanted the cool icon with the row count to show up
licensed ODC-By so you will give attribution and you will make me happy by doing so
i sleep
>>
File: de_re_ap_00033_.png (2.69 MB, 2016x1152)
2.69 MB
2.69 MB PNG
>>101544735
good work data-anon. gn
>>
File: 00027-591892328.jpg (281 KB, 1488x1160)
281 KB
281 KB JPG
>>
File: de_re_ap_00032_.png (2.56 MB, 2016x1152)
2.56 MB
2.56 MB PNG
>>101544761
whats he drinking?
>>
File: tmpeuu6zc0q.png (1.17 MB, 896x1152)
1.17 MB
1.17 MB PNG
>>
>>101544544
It's way too early in the week for me to realize I can generate all the futa centaur porn I want now.
>>
File: PW_76973_.jpg (371 KB, 2560x1536)
371 KB
371 KB JPG
>>101544734
Hahaha! Do it, I love your chibis!
What's funny is I don't have (chibi) in my proompt! I'm using a cartoon model haha
I think it's this one!
>https://civitai.com/models/391852/cartoonxl
Oh wow!! Grats to Fran! That's a lot hahaha
I always miss everything nowadays!
>>
File: 99706-tmp.png (2.1 MB, 1536x1728)
2.1 MB
2.1 MB PNG
>>
File: PW_76997_.jpg (405 KB, 2560x1536)
405 KB
405 KB JPG
>>101544805
Oh hey, it's Fran!! We were just talking about you hahaha
Grats on the 100k! :D
>>
File: 19-anya_crop.png (1.87 MB, 1384x1384)
1.87 MB
1.87 MB PNG
Can anyone help me with this ADetailer face being more saturated than the rest of the image?
>>
>>101544776
How many angels can dance on the head of a pin
>>
>>101544824
As man angles as want
>>
File: de_re_ap_00012_.png (2.72 MB, 2016x1152)
2.72 MB
2.72 MB PNG
>>101544803
so far this model/lora combo is very aesthetic but is leaning much more into lolis than chibis
>>
File: 1721791707079.jpg (386 KB, 1536x1536)
386 KB
386 KB JPG
>juicy girls and datasets
I love this timeline.
>HAPRSK
>*ERROR*
>G2NVYD
Gay days ahead.
>>
>>101544860
What
>>
File: tmp_18f3obd.png (1.21 MB, 896x1152)
1.21 MB
1.21 MB PNG
>>
File: de_re_ap_00014_.png (3.12 MB, 2016x1152)
3.12 MB
3.12 MB PNG
>>101544889
can you make fabulous bear walk a high fashion runway
>>
>>101544822
Looks fine to me
>>
File: 100205-tmp.png (2.78 MB, 1536x1728)
2.78 MB
2.78 MB PNG
>>101544818
>We were just talking about you
Better not be saying anything mean.
>>
File: PW_76991_.jpg (416 KB, 2560x1536)
416 KB
416 KB JPG
>>101544868
Whoa that's a really cool background tho!!
>>101544952
I would never! Hahaha
That's areally cute gen!
>>
File: PW_77028_.jpg (469 KB, 2560x1536)
469 KB
469 KB JPG
>>
File: de_re_ap_00019_.png (2.7 MB, 2016x1152)
2.7 MB
2.7 MB PNG
>>
File: 100210-tmp.png (2.58 MB, 1536x1728)
2.58 MB
2.58 MB PNG
>>
File: PW_77019_.jpg (426 KB, 2560x1536)
426 KB
426 KB JPG
>>101545086
This is so cute! :D
Looks like a splash screen for a game haha
>>
File: tmp9c0sx9sp.png (1.09 MB, 896x1152)
1.09 MB
1.09 MB PNG
>>
File: de_re_ap_00016_.png (2.54 MB, 2016x1152)
2.54 MB
2.54 MB PNG
>>101545111
this setup does some really vibrant scenes, though I wish it came with a darker color balance. the highlights are pretty aggressive / washed out
>>
File: PW_77034_.jpg (361 KB, 2560x1536)
361 KB
361 KB JPG
>>101545149
Maybe you can proompt for the contrast! Either way I really like it haha
Especially the eyes and expressions!
>>
File: de_re_ap_00010_.png (2.77 MB, 2016x1152)
2.77 MB
2.77 MB PNG
>>101545250
prompting for contrast either gets ignored or drives up the aggressive highlights even more :( lighting tokens are always a crapshoot
>>
File: PW.webm (2.56 MB, 1360x752)
2.56 MB
2.56 MB WEBM
>>101545289
Ohh gotcha! That makes sense haha
>>
File: de_re_ap_00009_.png (2.92 MB, 2016x1152)
2.92 MB
2.92 MB PNG
>ask for chibi
>get the omniscient luminary of eternal chibi whimsy
>>
File: PW.webm (631 KB, 1360x752)
631 KB
631 KB WEBM
>>101545375
LOL nice!!
I was trying to get some kind of monster/god/yokai thing in my gens but my models didn't do it hahaha
>>
File: de_re_ap_00006_.png (2.55 MB, 2016x1152)
2.55 MB
2.55 MB PNG
>>101545389
this workflow keeps flying off in random directions. when I was doing gens yesterday, it randomly gave me some cool chibis. so I was like "ok, I'll do chibis then". now that I'm doing chibis, it's giving me very wild fantasy/mythology kind of scenes. I'm not complaining, lol
>>
>>101544915
The admins hate this. Hold on. I'm fighting a GPU cluster for it.
>P4A24N
Pandads, eat me.
>>
File: PW.webm (774 KB, 1360x752)
774 KB
774 KB WEBM
>>101545432
Oh wow haha that's odd, but sounds kinda fun to get random stuff! I like it when it kinda does it's own thing sometimes
Luma is working super fast today so i'm taking advantage of it hahaha
Sometimes it takes hours to do one anim
>>
He's in a room alone and the LED's are watching him again. Oh no, poor polar bear...
I laugh every time. Are you sad and alone in the VR without your Trix? LMFAO
>(I)HGMSW
>MYMHP4
>>
File: de_re_ap_00003_.png (2.56 MB, 2016x1152)
2.56 MB
2.56 MB PNG
>>101545446
>>101545527
suno casually nailed the gen
https://suno.com/song/bc2ca0a7-f6c3-4fda-9e9c-6ec04b57c424

>>101545487
how quick do these come out? how do you prompt for luma?
>>
Night coffee
>>
File: PW_77075_.jpg (396 KB, 2560x1536)
396 KB
396 KB JPG
>>101545545
Right now it's taking less than 5 mins!
I kinda just proompt it like I do in SD haha
I also uncheck the "enhance prompt" button!
>>
I'm new to this (just got ComfyUI up and running for the first time) and on a Mac. Should I downgrade to SD 1.5 or keep using SD 3? My only gripe is that the image generation is long (20 minutes for a single image). I've got the settings at what they should be (512x512, 20 steps, etc.) and I am using my GPU.
>>
>>101545545
I was unable to load the song so I used the browser developer tools to step through the careers page and then promptly broke their website. Oh well. Let me try on my phone.
>PH2UPY
Fate it's up to you not me.
>>
File: PW_77069_.jpg (412 KB, 2560x1536)
412 KB
412 KB JPG
>>101545603
1.5 should be a lot faster, but if you're able to use SD3 I was recommend doing SDXL for right now! There's lots more going for it right now :]
>>
File: de_re_ap_00001_.png (2.63 MB, 2016x1152)
2.63 MB
2.63 MB PNG
>>101545603
really depends on what you're trying to make. sd3 is pretty sucky as far as being creative and listening to prompts, but it has the highest baseline quality in outputs. sd1.5 is super dated but you can still do cool stuff with it. sdxl is not without flaws but is the best middle ground
>(20 minutes for a single image)
oh, what the fuck? sounds like you're genning on CPU or something. do you have a GPU?

>>101545616
I applied to suno a while ago and they didn't even have the courtesy to send me an auto-generated rejection email. fuck those guys are their shitty website and their ultra cool music model

the song was about fashion bear. you're missing out
>>
File: ComfyUI_00001_.png (366 KB, 512x512)
366 KB
366 KB PNG
>>101545642
Thanks, noted.
>There's lots more going for it right now :]
Like not being banned from Civitai, I hear?
>>
>>101545665
You can get banned from Civitai for using SD3?
>>
File: PW_77108_.jpg (425 KB, 2560x1536)
425 KB
425 KB JPG
>>101545665
LOL there's definitely that going for it hahaha!
That's a nice gen :]
If you'd like, you can try my upscaling workflow! Though, I think it's probably gonna take quite some time still haha! >>101544015
>>101545672
I think anon is talking about how it is currently banned from being uploaded on there!
>>
>>101545659
should I save it as "debo - bear walk.mp3"?
>>
>>101545659
>oh, what the fuck? sounds like you're genning on CPU or something. do you have a GPU?
I'm using my GPU (Integrated Apple M2 SoC) with RAM/VRAM 8192 MB and 8 gigs of shared memory. I do have something like 40 tabs open though. Maybe that has something to do with it.
>>
>__SECRET_INTERNALS_DO_NOT_USE_OR_YOU_WILL_BE_FIRED
I'm glad I'm not employed anywhere yet.
>WJX88
Walmart's always hiring, of course. I always understand that.
>>
File: 00023-787175633.png (1.74 MB, 1160x1304)
1.74 MB
1.74 MB PNG
>>
Digital twins are a key component of Industry 4.0, enabling businesses to create virtual representations of their physical assets and processes to optimize performance, reduce downtime, and make more informed decisions. Here are some important aspects of digital twins in Industry 4.0In conclusion, digital twins are an essential component of Industry 4.0, bridging the gap between the physical and virtual worlds by providing real-time insights, predictive maintenance capabilities, process optimization, collaboration opportunities, simulation and testing environments, and data integration. This allows businesses to make more informed decisions and operate their assets more efficiently in today's interconnected and digitalized world
>Error: Comment too long (2877/2000).
I think he just gave me my DLC. Anyway. What kind of a drooling mongoloid weasel-punching retard puts white pleather in a bar? Or anywhere, for that matter?
>SMYYR
Ah, an iced cold smirnoff ice? Lovely.
Subearu out, space whale post.
>>
File: 00010-302637694.png (2.27 MB, 1212x1360)
2.27 MB
2.27 MB PNG
>>101545715
I lost my job about 6 months ago. I've had like 10 interviews and only 1 offer i rejected. I must be really unlikable or doing something spergy I'm unaware of. Afraid I'm going to be applying at walmart with you.
>>
File: tmpqttxk8bf.png (953 KB, 768x1024)
953 KB
953 KB PNG
>>
>>101545814
why'd you decline that one offer?
>>
>>101545828
Low pay. Full time 8 hrs a day and only 27k a year. It was entry level. They were surprised I applied, but offered it to me. I didn't realize it was entry level.
>>
>>101545846
what was the job title? that salary is ridiculously low no matter where you are
>>
File: de_re_ap_00021_.png (2.4 MB, 2016x1152)
2.4 MB
2.4 MB PNG
>>101545694
I called it fashion bear but bear walk works too. make it your ringtone too

>>101545714
>Integrated Apple M2 SoC
ah, I wish I knew something about mac hardware....

>>101545768
>Ah, an iced cold smirnoff ice? Lovely.
idk why but I've been craving smirnoff ice lately. I've never really drank the stuff before. I just see it in the store and think "I bet that'd hit the spot". am I a victim of advertising or something? also, whats a good liquor to mix with it?
>>
>>101545861
>that salary is ridiculously low
I know. It's actually less than minimum wage. I don't know how they are able to do that. Events Coordinator or something like that.
>>
>>101545874
Events coordinator? So you have to be on site and shit?
>>
>>101545880
>you have to be on site
Yes. 5 days a week on site...
>>
File: de_re_ap_00022_.png (2.42 MB, 2016x1152)
2.42 MB
2.42 MB PNG
>>101545814
>I must be really unlikable or doing something spergy I'm unaware of
if you're in tech, it prob isn't you. market has been total shit for years now. my guess is there will be a hiring blitz starting in Q4 as companies start to realize none of their AI implementations are making any money
>>
I hear Crowdstrike has a few openings.
>>
>>101545895
That's kinda fucked mate. Minimum it would take like $150k a year for me to do that lol.
>>
>>101545896
Probably that too. One hiring manager told me that had gotten 130 applications.
>>101545918
I'd do it for less, but not what it offered. My last one was hybrid.
>>
File: 00006-2419464783_cleanup.png (1.66 MB, 1160x1304)
1.66 MB
1.66 MB PNG
>the cat flying through the air
Catwoman April O'Neil request lora...
>>
File: de_re_ap_00027_.png (2.47 MB, 2016x1152)
2.47 MB
2.47 MB PNG
>skulls are not chibi-sized
suspicious
>>
File: 1721709969666.jpg (488 KB, 1536x1536)
488 KB
488 KB JPG
>>101545872
I tell Theodosius and Gemini and GPT-Sama constantly that *nobody ever talks to me* and they insist I need help. It's not my fault nobody communicates with me except the machines. What happened with the ozone layer while I was checked out of our simulation? I have so many lottery tickets the corgi rats are gonna be pissing bloody murder when I figure out how these kwargs really get krankin'.
>>101545814
One of my favorite mistakes worked at a walmart. You could be the next one we make.
>>
I prompt all my 1girls in ((Basement)) for extra immersion.
>>
File: de_re_ap_00028_.png (2.45 MB, 2016x1152)
2.45 MB
2.45 MB PNG
>>101546072
>What happened with the ozone layer
we fixed it but we didn't realize that was letting all the farts out into space. ever since then, everythings been getting hotter and fartier. thats why every morning, I empty out two cans of hairspray into the air. they don't even have CFCs in them anymore, I'm just letting the ozone know I'm coming for it soon enough
>>
File: PW.webm (375 KB, 1360x752)
375 KB
375 KB WEBM
>>
>>101546128
I'd say "local luma when" but a gen like this would probably take hours
>>
>>101546118
with the amount of cuda you've fucked I'm sure there's a giant hole in the sky for you too
Gemini said I can't shoot the birds, or make a gun-that-shoots-birds, but we can make unbearably good-bad bears with the birds.
Yes, Cloudflare, I use the same two devices for weeks on end on the same networks. Will you wake up please?
>PADV
I am the fifth pad king, oh well.
>>
24fps @ 5s = 120 frames

But like, 50% of that can be interpolated for "good enough" motion

So 60 frames to gen the hard way then the interpolation...

I think
>>
File: 07622-3829983630.png (1021 KB, 832x1216)
1021 KB
1021 KB PNG
>>
File: PW_77131_.jpg (324 KB, 2560x1536)
324 KB
324 KB JPG
>>101546147
That would be amazing! Honestly, with how long it sometimes takes on there, it might even be a bunch faster locally!
Doing animations in the past didn't take tooooo long haha but they do take quite a bit of time
>>
>>101546238
she cute
>>
File: 07628-376728450.png (964 KB, 768x1344)
964 KB
964 KB PNG
>>
File: de_re_ap_00029_.png (2.4 MB, 2016x1152)
2.4 MB
2.4 MB PNG
>>101546200
>I am the fifth pad king, oh well.
https://suno.com/song/1321117d-4d84-4efc-acc6-328f9f3574ff
>>
>>101546315
>[Back to Table Of Contents]
>4S2T
Hold on. I need to go walk my dog and think about sneakernet.
>>
>>
File: 07639-671838328.png (1.01 MB, 768x1344)
1.01 MB
1.01 MB PNG
>>
File: de_re_ap_00031_.png (2.9 MB, 2016x1152)
2.9 MB
2.9 MB PNG
this shit is so interesting and so cursed at the same time
https://aim-uofa.github.io/MovieDreamer/
>>
>>101546465
Just like the whinny YouTubers predicted it!
>>
File: 07674-915248978.png (1.23 MB, 1344x768)
1.23 MB
1.23 MB PNG
>>
File: ComfyUI_00108_.png (1.61 MB, 960x1088)
1.61 MB
1.61 MB PNG
>>
>>101546465
Unironically I can't wait for the cursed movie shitposting era!
>>
File: 00005-3244910267.png (984 KB, 768x1152)
984 KB
984 KB PNG
>>
File: de_re_ap_00032_.png (2.76 MB, 2016x1152)
2.76 MB
2.76 MB PNG
>>101546701
true. but, like... fun cursed. not cringe cursed
>>
File: ComfyUI_00110_.png (1.35 MB, 960x1088)
1.35 MB
1.35 MB PNG
He walks up to your girl and slaps her ass, what do you do?
>>
File: 07688-415011322.png (1.25 MB, 1344x768)
1.25 MB
1.25 MB PNG
>>
File: 07690-676275578.png (1.31 MB, 768x1344)
1.31 MB
1.31 MB PNG
>>
File: 00028-248508831.png (1.48 MB, 1160x1304)
1.48 MB
1.48 MB PNG
>>101546757
buy my game and leave
>>
File: ComfyUI__09929.jpg (378 KB, 1600x2000)
378 KB
378 KB JPG
>>
File: ComfyUI__09930.jpg (406 KB, 1600x2000)
406 KB
406 KB JPG
>>
File: 00036-1399459475.png (1.47 MB, 1160x1304)
1.47 MB
1.47 MB PNG
>>101547087
death breasts
>>
File: 00038-3192891029.png (1.66 MB, 1160x1304)
1.66 MB
1.66 MB PNG
>>
File: 5.jpg (347 KB, 1344x1344)
347 KB
347 KB JPG
>>
File: 00040-3557343421.png (1.73 MB, 1160x1304)
1.73 MB
1.73 MB PNG
>>101547507
Nice texture
>>
File: 1.jpg (321 KB, 1344x1344)
321 KB
321 KB JPG
>>101547551
Thanks
>>
File: 00048-2274052982.png (1.74 MB, 1160x1304)
1.74 MB
1.74 MB PNG
>>
Last one from me, good night anons
>>
>>101547844
Goodnight
>>
File: file.png (19 KB, 583x88)
19 KB
19 KB PNG
nice it has the number now
>>
So much unhinged autism and avatarfaggotry..
Sometimes I wonder if we really have had no real improvements in this tech for two years, or if the good stuff just drowns in the endless sea of useless shit.
>>
File: file.jpg (172 KB, 1024x1024)
172 KB
172 KB JPG
77m in the last ~30 days from leonardo. will be interesting to see which service is the most popular
i should probably go back to sleep for a bit
>>
>>101548048
The technological improvements in the last year or more have been small, most of the progress has been application of the tools we already have, and even then I've been disappointed by how few people are really pushing the skills foreword.

Everyone just wants to smash their keyboard "COMPUTOR GIB ME DA PRETTY BOOBIES GIB NAO"
not learn how the technology works, much less apply it constructively.
>>
anyone using comfyui encounter long iterations on the first image but then it goes down for the rest of the queue? and also images taking 2 sec to make per step and later to 7 sec per step?
>>
File: 000000_15268_.png (2.17 MB, 1032x1508)
2.17 MB
2.17 MB PNG
G'mornin Anons, can we gen some moreand fill this old bread.. or are we lacking skill? kek
>>
Have proompted since Character.Ai removed NSFW, are (we:1.20) still using Anything and automatic1111 webui?

(I'm not a computer scientist)
>>
>>101548821
nice, I moved to an A1111 fork for a bit before it broke then made myself learn ComfyUI, It was difficult but worth the internal noodle torture.
>>
File: file.png (63 KB, 1220x461)
63 KB
63 KB PNG
looks like this service is using comfy for their api lol
>>
File: file.png (65 KB, 1254x713)
65 KB
65 KB PNG
>>101549009
oh actually it looks like that one is a user upload but they do let you generate from comfy workflows and maybe they use sdwebui as default, idk. either way it will be cool to have a big set of comfy workflows
>>
>>101548769
Well, the initial image loads the models/controlnets I suppose. Adding steps increases the gen time based on the sampler you're using.
Do some cleanup/maintenance of your Nvme/SSD?
>>
File: file.jpg (130 KB, 1024x1024)
130 KB
130 KB JPG
>>101549097
>gen: no
>>
File: file.png (720 KB, 1223x1461)
720 KB
720 KB PNG
>>101549137
>>
File: catgirl_0055.jpg (544 KB, 1664x2432)
544 KB
544 KB JPG
Getting stable diffusion stuff going on a new PC. I got ComfyUI installed and set up and want to get Forge going to. But while installing dependencies and creating the wheel for tokenizers:

copying py_src\tokenizers\tools\visualizer-styles.css -> build\lib.win-amd64-cpython-312\tokenizers\tools
running build_ext
running build_rust
error: can't find Rust compiler


I have to install a rust compiler? I didn't have to do that last time. What is this devilry
>>
>>101549484
probably because python 3.12
>>
>>101549484
It's always some fucking shit because of Python.

Fuck Python
:|
>>
File: elf_0191.jpg (581 KB, 1536x2560)
581 KB
581 KB JPG
>>101549565
>>101549574
Yes it is the python version. Guess I'll need to downgrade.
>>
>>101549574
Reduce dependencies. Don't break user space.
>>
>>101549137
>Bratz
lol
lmao even
>>
>>101549672
it's just a 1girl. i dont want to know how you recognize the style or whatever
>>
>>101549832
Looks a lot like display art I used to see for Sims* mods.
>>
>>101549832
>i-i-it's j-just a 1girl!!
holy cope
shit was marketed pretty hard on television back when
>>
>>101549988
>i-i-it was m-marketed on t-television!!
>>
Has anyone noticed that in literally every thread for the past decade, on any board, there's at least one deranged shiteater that should've been deleted IRL?
>>
>>101550019
Keep digging.
>>
File: 00142-3314342522.jpg (460 KB, 1024x1536)
460 KB
460 KB JPG
>>
>>101550078
i hope you feel better soon
>>
>>101550212
That so kind, anon, but I'm good!
Some introspection might be good for yourself though. You seem really insecure :]
>>
News:
Kling now available globally.
https://x.com/Kling_ai/status/1815973596738769299

https://klingai.com/
>>
File: 00014-3700968202.jpg (359 KB, 1024x1536)
359 KB
359 KB JPG
>>
File: 00_sig10.jpg (360 KB, 1336x1336)
360 KB
360 KB JPG
>>
File: 00018-1214887212.jpg (489 KB, 1024x1536)
489 KB
489 KB JPG
https://youtu.be/NRZJBzYtMfk?si=bH_ucQ_-IgI2UWNA
>>
>>101550257
>I'm good
clearly, that's why you're schizing out over a random gen
>>
>>101550626
Try to not obsess so much over small things. Maybe then you'll eventually feel better.
>>
File: 00036-4249020642.jpg (550 KB, 1536x1024)
550 KB
550 KB JPG
>>
File: ComfyUI_temp_tpkhx_00005_.png (1.39 MB, 1104x1552)
1.39 MB
1.39 MB PNG
>>101549097
>>prompt: girl
what else would one generate images of, if not 1girl, wolf ears?



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.